Undress to Redress: A Training-Free Framework for Virtual Try-On

TL;DR

UR-VTON is a training-free virtual try-on framework that improves short-sleeve garment synthesis by decomposing the task into undressing and redressing steps, enhancing realism and detail fidelity.

Contribution

It introduces a novel undress-to-redress mechanism and integrates guidance scheduling and structural refinement, enabling better long-sleeve-to-short-sleeve try-on without additional training.

Findings

Outperforms state-of-the-art in detail preservation

Achieves higher image quality in try-on results

Introduces LS-TON benchmark for long-sleeve-to-short-sleeve tasks

Abstract

Virtual try-on (VTON) is a crucial task for enhancing user experience in online shopping by generating realistic garment previews on personal photos. Although existing methods have achieved impressive results, they struggle with long-sleeve-to-short-sleeve conversions-a common and practical scenario-often producing unrealistic outputs when exposed skin is underrepresented in the original image. We argue that this challenge arises from the ''majority'' completion rule in current VTON models, which leads to inaccurate skin restoration in such cases. To address this, we propose UR-VTON (Undress-Redress Virtual Try-ON), a novel, training-free framework that can be seamlessly integrated with any existing VTON method. UR-VTON introduces an ''undress-to-redress'' mechanism: it first reveals the user's torso by virtually ''undressing,'' then applies the target short-sleeve garment, effectively decomposing the conversion into two more manageable steps. Additionally, we incorporate Dynamic Classifier-Free Guidance scheduling to balance diversity and image quality during DDPM sampling, and employ Structural Refiner to enhance detail fidelity using high-frequency cues. Finally, we present LS-TON, a new benchmark for long-sleeve-to-short-sleeve try-on. Extensive experiments demonstrate that UR-VTON outperforms state-of-the-art methods in both detail preservation and image quality. Code will be released upon acceptance.